Skip to content

@DS4SD IBM Deep Search

Change the repository type filter

All

    Repositories list

    25 repositories

    • docling

      Public
      Get your documents ready for gen AI
      htmlmarkdownpdfaiconvertxlsxpdf-converterdocxdocumentspptx
      Python
      •
      MIT License
      •946•18k•126•14•Updated Jan 10, 2025Jan 10, 2025

    • docling-ibm-models

      Public
      Python
      •
      MIT License
      •10•61•12•1•Updated Jan 10, 2025Jan 10, 2025

    • docling-core

      Public
      A python library to define and validate data types in Docling.
      Python
      •
      MIT License
      •24•50•7•2•Updated Jan 10, 2025Jan 10, 2025

    • docling-haystack

      Public
      Docling Haystack integration
      Python
      •
      MIT License
      •0•10•2•0•Updated Jan 9, 2025Jan 9, 2025

    • deepsearch-examples

      Public
      Examples using the Deep Search functionalities
      Python
      •
      MIT License
      •18•52•0•4•Updated Jan 9, 2025Jan 9, 2025

    • docling-langchain

      Public
      Docling LangChain integration
      Python
      •
      MIT License
      •0•4•0•0•Updated Jan 9, 2025Jan 9, 2025

    • docling-serve

      Public
      Running Docling as an API service
      Python
      •
      MIT License
      •10•38•3•4•Updated Dec 19, 2024Dec 19, 2024

    • .github

      Public
      0•1•0•1•Updated Dec 16, 2024Dec 16, 2024

    • docling-parse

      Public
      Simple package to extract text with coordinates from programmatic PDFs
      C++
      •
      MIT License
      •10•44•12•0•Updated Dec 16, 2024Dec 16, 2024

    • deepsearch-toolkit

      Public
      Interact with the Deep Search platform for new knowledge explorations and discoveries
      nlppdf-converterknowledge-graphragknowledge-extractionsemantic-retrievalaccelerated-discoverydeepsearchpython
      Python
      •
      MIT License
      •22•144•8•12•Updated Dec 9, 2024Dec 9, 2024

    • deepsearch-glm

      Public
      Create fast graph language models from converted PDF documents for knowledge extraction and Q&A.
      C++
      •
      MIT License
      •7•32•2•1•Updated Dec 9, 2024Dec 9, 2024

    • DS4SD.github.io

      Public
      CSS
      •
      MIT License
      •1•10•0•0•Updated Dec 2, 2024Dec 2, 2024

    • PatCID

      Public
      Python
      •
      MIT License
      •1•36•2•0•Updated Nov 28, 2024Nov 28, 2024

    • MolDepictor

      Public
      MolGrapher: Graph-based Visual Recognition of Chemical Structures
      Python
      •
      MIT License
      •0•9•0•0•Updated Nov 28, 2024Nov 28, 2024

    • MolGrapher

      Public
      MolGrapher: Graph-based Visual Recognition of Chemical Structures
      Python
      •
      MIT License
      •3•59•0•0•Updated Nov 22, 2024Nov 22, 2024

    • quackling

      Public archive
      Build document-native LLM applications
      pythonpdfaidocumentchunkingraglangchainllamaindex
      Python
      •
      MIT License
      •2•52•0•0•Updated Sep 11, 2024Sep 11, 2024

    • project-mognet

      Public
      Mognet is a fast, simple framework to build distributed applications using task queues.
      Python
      •
      MIT License
      •4•10•0•1•Updated Aug 7, 2024Aug 7, 2024

    • MolAnnotator

      Public
      Python
      •
      MIT License
      •0•7•0•0•Updated Jul 8, 2024Jul 8, 2024

    • MolClassifier

      Public
      Python
      •
      MIT License
      •0•8•0•0•Updated Jul 8, 2024Jul 8, 2024

    • SemTabNet

      Public
      Repository for ACL paper: "Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs"
      Python
      •
      MIT License
      •1•10•0•0•Updated Jul 1, 2024Jul 1, 2024

    • deepsearch4czi

      Public
      Repository to detect scientific software in documents for Chan Zuckerberg Initiative workshop
      Python
      •
      MIT License
      •1•2•0•0•Updated Oct 26, 2023Oct 26, 2023

    • langchain

      Public
      ⚡ Building applications with LLMs through composability ⚡
      Python
      •
      MIT License
      •16k•1•0•0•Updated May 18, 2023May 18, 2023

    • icdar23-doclaynet

      Public
      Website of the ICDAR 2023 DocLayNet competition
      2•1•0•0•Updated Apr 26, 2023Apr 26, 2023

    • DocLayNet

      Public
      DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis
      Other
      •16•300•3•0•Updated Feb 1, 2023Feb 1, 2023

    • deepsearch-nlp-annotator-api-example

      Public template
      Example NLP Annotator API used for integrating with the IBM DeepSearch CPS platform
      Python
      •
      Apache License 2.0
      •4•10•0•0•Updated Sep 8, 2022Sep 8, 2022